The recognition method of external force damage sources vibration signals based on LSTM-CNN-CatBoost-GSSSA
Xiaojuan Chen, Lufan Zhang, Xue Li, Funan Gao · 2026
Read The recognition method of external force damage sources vibration signals based on LSTM-CNN-CatBoost-GSSSA by Xiaojuan Chen, Lufan Zhang, Xue Li, Funan Gao (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0344678.txt.
Description
Xiaojuan Chen, Lufan Zhang, Xue Li, and Funan Gao built a listening system that identifies what is threatening buried fibre-optic cables under city streets. Construction digs and manual excavation near these power-grid communication cables cause frequent damage, and the vibrations they make differ subtly. Their 2026 model stacks several learning methods, reading the vibration's timing, frequency, and spread, with an improved search algorithm tuning the ensemble.
In experiments the hybrid reached about ninety-eight percent recognition accuracy, edging out six rival approaches, some by wide margins, while staying fast enough for live monitoring. The authors present it as a practical early-warning tool that helps crews protect urban power communication networks from accidental strikes.
Catalog record
| CREATOR | Xiaojuan Chen, Lufan Zhang, Xue Li, Funan Gao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50720 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |